Mercurial > repos > greg > vsnp_get_snps
annotate vsnp_get_snps.xml @ 13:cd636b0e4f95 draft
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit cab8ee43e902a3ae7b0fd6b06842c4b5c221af25"
author | greg |
---|---|
date | Tue, 21 Sep 2021 00:21:36 +0000 |
parents | 544b2ed99a9a |
children | 44b84d32883c |
rev | line source |
---|---|
10 | 1 <tool id="vsnp_get_snps" name="vSNP: get SNPs" version="@WRAPPER_VERSION@.1+galaxy0" profile="@PROFILE@"> |
0 | 2 <description></description> |
3 | 3 <macros> |
4 <import>macros.xml</import> | |
5 </macros> | |
0 | 6 <requirements> |
10 | 7 <expand macro="openpyxl_requirement"/> |
8 <expand macro="pandas_requirement"/> | |
9 <expand macro="pyvcf_requirement"/> | |
10 <expand macro="xlrd_requirement"/> | |
0 | 11 </requirements> |
12 <command detect_errors="exit_code"><![CDATA[ | |
3 | 13 #import re |
14 | |
0 | 15 #set input_vcf_dir = 'input_vcf_dir' |
16 #set output_json_avg_mq_dir = 'output_json_avg_mq_dir' | |
17 #set output_json_snps_dir = 'output_json_snps_dir' | |
18 #set output_snps_dir = 'output_snps_dir' | |
3 | 19 |
0 | 20 mkdir -p $input_vcf_dir && |
21 mkdir -p $output_json_avg_mq_dir && | |
22 mkdir -p $output_json_snps_dir && | |
23 mkdir -p $output_snps_dir && | |
3 | 24 |
12 | 25 #if str($input_additional_zc_vcf_collection_cond.input_additional_zc_vcf_collection) =='yes': |
26 #set dbkey = '?' | |
27 #for $i in $input_additional_zc_vcf_collection_cond.input_vcf_collection: | |
28 #if str($dbkey) == '?': | |
29 #set dbkey = $i.metadata.dbkey | |
30 #else if str($dbkey) != $i.metadata.dbkey: | |
13
cd636b0e4f95
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit cab8ee43e902a3ae7b0fd6b06842c4b5c221af25"
greg
parents:
12
diff
changeset
|
31 >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique, check ${i.name}" && exit 1 |
12 | 32 #end if |
33 #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) | |
34 ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' && | |
35 #end for | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
36 #if str($dbkey) == '?': |
12 | 37 >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1 |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
38 #end if |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
39 #end if |
3 | 40 #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single": |
41 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier)) | |
42 ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 43 #else |
44 #for $i in $input_zc_vcf_type_cond.input_zc_vcf_collection: | |
3 | 45 #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) |
46 ln -s '${i}' '$input_vcf_dir/${zc_vcf_identifier}' && | |
0 | 47 #end for |
48 #end if | |
3 | 49 #if str($input_excel_cond.input_excel_param) == 'yes': |
50 #if str($input_excel_cond.excel_source_cond.excel_source) == 'cached': | |
51 #set excel_file = 'No genome specified for input VCF (database) file(s)' | |
0 | 52 #set excel_fields = $__app__.tool_data_tables['vsnp_excel'].get_fields() |
10 | 53 ## The value of excel_fields is a nested list that looks like this. |
3 | 54 ## [['AF2122', 'Mbovis_define_filter.xlsx', '~/tool-data/vsnp/AF2122/excel/Mbovis_define_filter.xlsx', 'Excel file for AF2122'],...] |
0 | 55 #for $i in $excel_fields: |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
56 #if str($i[0]) == $dbkey: |
0 | 57 #set excel_file = $i[2] |
58 #break | |
59 #end if | |
60 #end for | |
61 #else: | |
3 | 62 #set excel_file = $input_excel_cond.excel_source_cond.input_excel |
0 | 63 #end if |
64 #end if | |
65 python '$__tool_directory__/vsnp_get_snps.py' | |
3 | 66 --ac $ac |
67 #if str($input_excel_cond.input_excel_param) == 'yes': | |
68 --input_excel '$excel_file' | |
0 | 69 #end if |
3 | 70 $all_isolates |
71 --input_vcf_dir '$input_vcf_dir' | |
72 --min_mq $min_mq | |
73 --min_quality_score $min_quality_score | |
74 --output_json_avg_mq_dir '$output_json_avg_mq_dir' | |
75 --output_json_snps_dir '$output_json_snps_dir' | |
76 --output_snps_dir '$output_snps_dir' | |
0 | 77 --output_summary '$output_summary' |
3 | 78 --processes \${GALAXY_SLOTS:-8} |
79 --quality_score_n_threshold $quality_score_n_threshold | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
80 --dbkey '$dbkey' |
0 | 81 ]]></command> |
82 <inputs> | |
83 <conditional name="input_zc_vcf_type_cond"> | |
84 <param name="input_zc_vcf_type" type="select" label="Choose the category of the files to be analyzed"> | |
3 | 85 <option value="collection" selected="true">A collection of zero coverage VCF files</option> |
86 <option value="single">A single zero coverage VCF file</option> | |
0 | 87 </param> |
88 <when value="single"> | |
3 | 89 <param name="input_zc_vcf" type="data" format="vcf" label="Zero coverage VCF file"/> |
0 | 90 </when> |
91 <when value="collection"> | |
3 | 92 <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/> |
0 | 93 </when> |
94 </conditional> | |
12 | 95 <conditional name="input_additional_zc_vcf_collection_cond"> |
96 <param name="input_additional_zc_vcf_collection" type="select" label="Include an additional collection of curated zero-coverage VCF files?"> | |
97 <option value="no" selected="true">No</option> | |
98 <option value="yes">Yes</option> | |
99 </param> | |
100 <when value="no"/> | |
101 <when value="yes"> | |
102 <param name="input_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files with SNPs found in closely related isolate groups"/> | |
103 </when> | |
104 </conditional> | |
3 | 105 <param name="ac" type="integer" min="0" value="2" label="Allele count threshold" help="At least 1 position must have this value for a SNP to be added to a group"/> |
106 <param name="min_mq" type="integer" min="0" value="56" label="Map quality threshold" help="At least 1 position must have a higher MQ value for a SNP to be added to a group"/> | |
107 <param name="min_quality_score" type="integer" min="0" value="150" label="Quality score threshold" help="At least 1 position must have a higher quality score for a SNP to be added to a group"/> | |
108 <param name="quality_score_n_threshold" type="integer" min="0" value="150" label="Minimum quality score N value for alleles" help="Alleles are marked as N for quality scores between this value and the minimum quality score value above"/> | |
109 <conditional name="input_excel_cond"> | |
110 <param name="input_excel_param" type="select" label="Use Excel file for grouping and filtering?"> | |
0 | 111 <option value="yes" selected="true">Yes</option> |
112 <option value="no">No</option> | |
113 </param> | |
114 <when value="yes"> | |
3 | 115 <conditional name="excel_source_cond"> |
116 <param name="excel_source" type="select" label="Choose the source for the Excel file"> | |
0 | 117 <option value="cached">locally cached</option> |
118 <option value="history">from history</option> | |
119 </param> | |
120 <when value="cached"> | |
3 | 121 <param name="input_excel" type="select" label="Excel file"> |
122 <options from_data_table="vsnp_excel"> | |
123 <validator type="no_options" message="No built-in Excel grouping and filtering datasets are available"/> | |
124 </options> | |
0 | 125 </param> |
126 </when> | |
127 <when value="history"> | |
3 | 128 <param name="input_excel" type="data" format="xlsx" label="Excel file"/> |
0 | 129 </when> |
130 </conditional> | |
131 </when> | |
132 <when value="no"/> | |
133 </conditional> | |
10 | 134 <param argument="all_isolates" type="boolean" truevalue="--all_isolates" falsevalue="" checked="true" label="Create a group containing all isolates?"/> |
0 | 135 </inputs> |
136 <outputs> | |
3 | 137 <collection name="snps" type="list" label="${tool.name} on ${on_string} (SNPs)"> |
138 <discover_datasets pattern="__name_and_ext__" directory="output_snps_dir"/> | |
0 | 139 </collection> |
3 | 140 <collection name="json_avg_mq" type="list" label="${tool.name} on ${on_string} (average mq)"> |
141 <discover_datasets pattern="__name_and_ext__" directory="output_json_avg_mq_dir"/> | |
0 | 142 </collection> |
3 | 143 <collection name="json_snps" type="list" label="${tool.name} on ${on_string} (SNPs as json)"> |
144 <discover_datasets pattern="__name_and_ext__" directory="output_json_snps_dir"/> | |
0 | 145 </collection> |
3 | 146 <data name="output_summary" format="html" label="${tool.name} on ${on_string} (summary)"/> |
0 | 147 </outputs> |
148 <tests> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
149 <!-- |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
150 Unfortunately the test files cannot be gzipped since Galaxy changes the file names |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
151 to be something like 00-0121_WI_Cervid_99-A_vcf_gz, and the VCF Reader requires |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
152 gzipped files to have a .gz extension. The exception is |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
153 UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
154 --> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
155 <!-- A single vcf input, no excel file, all_isolates is False --> |
3 | 156 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
157 <param name="input_zc_vcf_type" value="single"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
158 <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/> |
12 | 159 <param name="input_additional_zc_vcf_collection" value="yes"/> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
160 <param name="input_vcf_collection"> |
0 | 161 <collection type="list"> |
162 <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/> | |
163 <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/> | |
164 </collection> | |
165 </param> | |
3 | 166 <param name="input_excel_param" value="no"/> |
10 | 167 <param name="all_isolates" value=""/> |
3 | 168 <output_collection name="snps" type="list" count="1"> |
169 <element name="all_vcf" file="all_vcf.fasta" ftype="fasta" compare="contains"/> | |
0 | 170 </output_collection> |
3 | 171 <output_collection name="json_avg_mq" type="list" count="1"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
172 <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> |
0 | 173 </output_collection> |
3 | 174 <output_collection name="json_snps" type="list" count="1"> |
175 <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> | |
0 | 176 </output_collection> |
177 <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> | |
178 </test> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
179 <!-- An input collection, no excel file, all_isolates is False --> |
3 | 180 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
181 <param name="input_zc_vcf_type" value="collection"/> |
3 | 182 <param name="input_zc_vcf_collection"> |
183 <collection type="list"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
184 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
185 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
186 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
187 </param> |
12 | 188 <param name="input_additional_zc_vcf_collection" value="yes"/> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
189 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
190 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
191 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
192 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
193 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
194 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
195 </param> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
196 <param name="input_excel_param" value="no"/> |
10 | 197 <param name="all_isolates" value=""/> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
198 <output_collection name="snps" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
199 <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
200 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
201 <output_collection name="json_avg_mq" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
202 <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
203 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
204 <output_collection name="json_snps" type="list" count="1"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
205 <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
206 </output_collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
207 <output name="output_summary" file="output_summary2.html" ftype="html" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
208 </test> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
209 <!-- An input collection, an excel file, all_isolates is False --> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
210 <test expect_num_outputs="4"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
211 <param name="input_zc_vcf_type" value="collection"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
212 <param name="input_zc_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
213 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
214 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
215 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
216 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
217 </param> |
12 | 218 <param name="input_additional_zc_vcf_collection" value="yes"/> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
219 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
220 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
221 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
222 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
223 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
3 | 224 </collection> |
225 </param> | |
226 <param name="input_excel_param" value="yes"/> | |
227 <param name="input_excel" value="89"/> | |
10 | 228 <param name="all_isolates" value=""/> |
3 | 229 <output_collection name="snps" type="list" count="1"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
230 <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> |
3 | 231 </output_collection> |
232 <output_collection name="json_avg_mq" type="list" count="1"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
233 <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 234 </output_collection> |
235 <output_collection name="json_snps" type="list" count="1"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
236 <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 237 </output_collection> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
238 <output name="output_summary" file="output_summary3.html" ftype="html" compare="contains"/> |
3 | 239 </test> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
240 <!-- An input collection, an excel file, all_isolates is True --> |
3 | 241 <test expect_num_outputs="4"> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
242 <param name="input_zc_vcf_type" value="collection"/> |
3 | 243 <param name="input_zc_vcf_collection"> |
244 <collection type="list"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
245 <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
246 <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
247 </collection> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
248 </param> |
12 | 249 <param name="input_additional_zc_vcf_collection" value="yes"/> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
250 <param name="input_vcf_collection"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
251 <collection type="list"> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
252 <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
253 <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
254 <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> |
3 | 255 </collection> |
256 </param> | |
257 <param name="input_excel_param" value="yes"/> | |
258 <param name="input_excel" value="89"/> | |
259 <param name="all_isolates" value="--all_isolates"/> | |
260 <output_collection name="snps" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
261 <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
262 <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> |
3 | 263 </output_collection> |
264 <output_collection name="json_avg_mq" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
265 <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
266 <element name="all_vcf" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> |
3 | 267 </output_collection> |
268 <output_collection name="json_snps" type="list" count="2"> | |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
269 <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
270 <element name="all_vcf" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> |
3 | 271 </output_collection> |
9
0fe292b20b9d
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
greg
parents:
8
diff
changeset
|
272 <output name="output_summary" file="output_summary4.html" ftype="html" compare="contains"/> |
3 | 273 </test> |
0 | 274 </tests> |
275 <help> | |
276 **What it does** | |
277 | |
3 | 278 Accepts a zero coverage VCF file produced by the **vSNP: add zero coverage** tool (or a collection of them) along with a collection |
279 of zero coverage VCF files that have been aligned with the same reference and contain SNPs called between closely related isolate groups. | |
280 The tool produces fasta files containing SNP alignments, json files containing the SNP positions and additional json files containing | |
281 the average map quality values. | |
282 | |
283 The SNP alignments produced by this tool are used to create phylogenetic trees, so larger input collections result in more populated | |
284 phylogenetic trees. Both of the json outputs are used by the **vSNP: build tables** tool to produce annotated SNP tables in the form | |
285 of Excel spreadsheets. | |
286 | |
287 An Excel spreadsheet containing specified SNPs can optiomally be used to filter desired SNP positions by group. Users can choose a | |
288 locally cached Excel spreadsheet or one from their current history. | |
289 | |
290 A SNP is added to a group if it has at least one position with a specified allele count value, a quality score greater than a specified | |
291 value, and a map quality greater than a specified value. | |
292 | |
293 If the allele count equals the specified value (2) and the quality score for a SNP position is greater than the minimum quality score | |
294 value (150), the alternate allele is called. | |
295 | |
296 However, if the allele count is 1, the position is called ambiguous. Deletions are called when the alternate allele is a gap. If the | |
297 quality score is less than or equal to the minimum quality score N value for alleles (150), the allele is marked "N". | |
0 | 298 |
299 **Required Options** | |
300 | |
3 | 301 * **Zero coverage VCF file(s)** - Select a single or collection of zero coverage VCF files, typically produced by the **vSNP: add zero coverage** tool, from the current history. |
302 * **Collection of zero coverage VCF files with SNPs found in closely related isolate groups** - Select a dataset collection of zero coverage vcf files from the current history. | |
0 | 303 |
304 **Additional Options** | |
305 | |
3 | 306 * **Allele count threshold** - At least 1 position must have an allele count greater than this value for a SNP to be added to a group (2 is optimal). |
307 * **Map quality threshold** - At least 1 position must have a higher MQ value for a SNP to be added to a group (56 is optimal). | |
308 * **Quality score threshold** -At least 1 position must have a higher quality score for a SNP to be added to a group (150 is optimal). | |
309 * **Minimum quality score N value for alleles** - If none of the avove 3 requirements is met and the quality score is less than or equal to the minimum quality score N value for alleles, the allele is marked "N" (150 is optimal). | |
0 | 310 * **Use Excel file for grouping and filtering?** - select Yes to filter desired SNP positions by group. A cached Excel spreadsheet provides the most widely used SNP positions for grouping, but a custom spreadhseet can be selected from the current history. |
3 | 311 * **Create a group containing all isolates?** - select Yes to output an additional group containing of all isolates. |
0 | 312 </help> |
3 | 313 <expand macro="citations"/> |
0 | 314 </tool> |
315 |